© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29759
    Prev
    Next
    INDEX
    Explanations

    walking and pedestrian movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æģĭ
    -0.10
    ç±į
    -0.10
    ç²ľ
    -0.09
     springs
    -0.09
    è·ĥ
    -0.09
    æ¸Ĭ
    -0.09
    ?url
    -0.09
    象å¾ģ
    -0.09
    å©ļ礼
    -0.09
    çģ¯çģ«
    -0.09
    POSITIVE LOGITS
    æŃ¥è¡Į
    0.12
     walking
    0.10
    ÑĮе
    0.09
    æŃ©
    0.09
     walker
    0.09
    è¿Īåĩº
    0.09
    èµ°å¾Ĺ
    0.09
    æĹĮ
    0.09
     Walking
    0.09
     walk
    0.09
    Activations Density 0.173%

    No Known Activations